© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212139
    Prev
    Next
    INDEX
    Explanations

    metal aluminum

    np_acts-logits-general · gemini-2.5-flash-lite

    aluminum, metal, Utah

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    临床
    0.52
    elser
    0.52
    涫
    0.51
    тории
    0.50
    胧
    0.50
    قى
    0.50
    Aren
    0.49
    cheidet
    0.49
    变化
    0.48
    ラ
    0.48
    POSITIVE LOGITS
    0.57
     aluminum
    0.56
     Metal
    0.55
     metal
    0.52
     METAL
    0.51
     anc
    0.50
     MAT
    0.49
     DIN
    0.49
     Anc
    0.48
     ya
    0.48
    Activations Density 0.001%

    No Known Activations